{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48532915115356445, "min": 0.48532915115356445, "max": 1.4759001731872559, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14342.447265625, "min": 14342.447265625, "max": 44772.90625, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.273602157831192, "min": -0.11658629775047302, "max": 0.3717784285545349, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.68376159667969, "min": -28.09729766845703, "max": 98.52128601074219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.033788811415433884, "min": -0.0004030598793178797, "max": 0.2483881711959839, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.852668762207031, "min": -0.10278026759624481, "max": 59.861549377441406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07044398076236359, "min": 0.06493134502685945, "max": 0.07416484683218177, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9862157306730903, "min": 0.5115191290431371, "max": 1.0161688930272836, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01221323648184937, "min": 0.00017596104073938648, "max": 0.013805589560888025, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17098531074589118, "min": 0.002287493529612024, "max": 0.20708384341332037, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.339040410828567e-06, "min": 7.339040410828567e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010274656575159994, "min": 0.00010274656575159994, "max": 0.003255547714817499, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244631428571428, "min": 0.10244631428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342484, "min": 1.3886848, "max": 2.4013729, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025438679714285704, "min": 0.00025438679714285704, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035614151599999986, "min": 0.0035614151599999986, "max": 0.10853973175000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012591413222253323, "min": 0.012591413222253323, "max": 0.36816316843032837, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17627978324890137, "min": 0.17627978324890137, "max": 2.5771422386169434, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 546.6909090909091, "min": 464.55555555555554, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30068.0, "min": 15984.0, "max": 34122.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.162298152798956, "min": -1.0000000521540642, "max": 1.3766507695591639, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 63.926398403942585, "min": -31.99920167028904, "max": 86.72899848222733, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.162298152798956, "min": -1.0000000521540642, "max": 1.3766507695591639, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 63.926398403942585, "min": -31.99920167028904, "max": 86.72899848222733, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07124370510203086, "min": 0.06367752091388129, "max": 7.45247757807374, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9184037806116976, "min": 3.9184037806116976, "max": 119.23964124917984, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679940175", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679942320" }, "total": 2144.8456532789996, "count": 1, "self": 0.4800676830000157, "children": { "run_training.setup": { "total": 0.1170124450000003, "count": 1, "self": 0.1170124450000003 }, "TrainerController.start_learning": { "total": 2144.2485731509996, "count": 1, "self": 1.617481003944249, "children": { "TrainerController._reset_env": { "total": 6.328256542999952, "count": 1, "self": 6.328256542999952 }, "TrainerController.advance": { "total": 2136.2021824160556, "count": 63309, "self": 1.6692377430799752, "children": { "env_step": { "total": 1487.1803434550134, "count": 63309, "self": 1362.484800516, "children": { "SubprocessEnvManager._take_step": { "total": 123.72251842600076, "count": 63309, "self": 5.448674193954503, "children": { "TorchPolicy.evaluate": { "total": 118.27384423204626, "count": 62564, "self": 118.27384423204626 } } }, "workers": { "total": 0.9730245130126605, "count": 63309, "self": 0.0, "children": { "worker_root": { "total": 2138.7539942390654, "count": 63309, "is_parallel": true, "self": 906.5827313251461, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017833819999850675, "count": 1, "is_parallel": true, "self": 0.000591094999890629, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011922870000944386, "count": 8, "is_parallel": true, "self": 0.0011922870000944386 } } }, "UnityEnvironment.step": { "total": 0.05094341900007748, "count": 1, "is_parallel": true, "self": 0.0005322329998307396, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005456080000385555, "count": 1, "is_parallel": true, "self": 0.0005456080000385555 }, "communicator.exchange": { "total": 0.047955507000096986, "count": 1, "is_parallel": true, "self": 0.047955507000096986 }, "steps_from_proto": { "total": 0.001910071000111202, "count": 1, "is_parallel": true, "self": 0.0004446799998731876, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014653910002380144, "count": 8, "is_parallel": true, "self": 0.0014653910002380144 } } } } } } }, "UnityEnvironment.step": { "total": 1232.1712629139192, "count": 63308, "is_parallel": true, "self": 33.21697740889522, "children": { "UnityEnvironment._generate_step_input": { "total": 25.76151679804161, "count": 63308, "is_parallel": true, "self": 25.76151679804161 }, "communicator.exchange": { "total": 1070.211174821971, "count": 63308, "is_parallel": true, "self": 1070.211174821971 }, "steps_from_proto": { "total": 102.9815938850113, "count": 63308, "is_parallel": true, "self": 22.428296003890182, "children": { "_process_rank_one_or_two_observation": { "total": 80.55329788112113, "count": 506464, "is_parallel": true, "self": 80.55329788112113 } } } } } } } } } } }, "trainer_advance": { "total": 647.3526012179623, "count": 63309, "self": 2.7854859419096556, "children": { "process_trajectory": { "total": 126.12455286105796, "count": 63309, "self": 125.84312547805757, "children": { "RLTrainer._checkpoint": { "total": 0.2814273830003913, "count": 2, "self": 0.2814273830003913 } } }, "_update_policy": { "total": 518.4425624149947, "count": 439, "self": 328.7447861779799, "children": { "TorchPPOOptimizer.update": { "total": 189.69777623701475, "count": 22824, "self": 189.69777623701475 } } } } } } }, "trainer_threads": { "total": 1.4019997252034955e-06, "count": 1, "self": 1.4019997252034955e-06 }, "TrainerController._save_models": { "total": 0.1006517860000713, "count": 1, "self": 0.001540923999982624, "children": { "RLTrainer._checkpoint": { "total": 0.09911086200008867, "count": 1, "self": 0.09911086200008867 } } } } } } }